© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135370
    Prev
    Next
    INDEX
    Explanations

    high energy scales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    섬
    0.39
    Archer
    0.38
    вик
    0.38
    risque
    0.38
    َرَ
    0.37
    Ris
    0.36
    {|\
    0.36
    燉
    0.36
     tower
    0.35
    Tower
    0.35
    POSITIVE LOGITS
     GU
    0.50
     Binding
    0.44
     Union
    0.43
     EditorGUILayout
    0.41
     Gu
    0.41
     GUS
    0.41
    GUILayout
    0.40
     WPARAM
    0.40
     Param
    0.40
     Swain
    0.40
    Activations Density 0.000%

    No Known Activations